Prediction of soil organic carbon and total nitrogen affected by mine using Vis–NIR spectroscopy coupled with machine learning algorithms in calcareous soils

Abstract

Abstract The utilization of visible-near infrared (Vis–NIR) spectroscopy presents a nondestructive, fast, reliable and cost-effective approach to predicting total nitrogen (TN) and organic carbon (OC) levels. This study employed a combination of Vis–NIR spectroscopy, partial least-squares regression (PLSR), and support vector machine (SVM) models to investigate the effects of mining on TN and OC stocks in both the topsoil (0–10 cm) and subsoil (10–40 cm). 105 soil samples were collected from agricultural areas near an iron mine, polluted, moderately-polluted, and non-polluted sites. Results indicated that soils at the non-polluted site had the highest of soil OC stocks (7.5 kg m–2) and total nitrogen (2.5 kg m–2), followed by the moderately-polluted site. Furthermore, it was observed that soils from the polluted site displayed the highest spectral reflectance. The spectral bands in the range of 500–700 nm showed the strongest correlation with soil organic carbon content. Notably, the SVM method utilizing Vis–NIR spectroscopy provided superior predictions for both subsoil and topsoil organic carbon and total nitrogen compared to the PLSR methods. Additionally, SVM demonstrated better performance in predicting topsoil soil organic carbon (R2 = 0.87, RMSE = 0.13%, and RPD = 2.8) and total nitrogen (R2 = 0.91, RMSE = 0.13%, and RPD = 2.4) compared to the subsoil, owing to the larger OM content in the topsoils.

Keywords

• SVM
• PLSR
• Spectra
• Mine